Ecuador sequencing data

---

Data for each isolate

---

data <- readRDS(here::here("data", "sequencing_log_summary.rds"))
data %>% 
    datatable(extensions = "Buttons", 
  #           options = list(dom = "Bfrtip", 
  #                          buttons = (list(
  #                            "copy", list(
  #                              extend = "collection", 
  #                              buttons = c("csv", "excel"), 
  #                              text = "Download")))), 
            rownames = F, 
            filter = "top",
            style = "bootstrap")

---

Summary all 65 isolates

---

totals <- data %>% adorn_totals() %>% filter(Sample == "Total") 
totals %>% kable() %>% kable_styling(full_width = F)

Sample	PreMerge	Merged	Discarded	NotAssembled	Filtered	Chimeric	Centroids	Centroidswithsupport	Aftercontaminantfiltering	3D7	DD2	HB3
Total	6929470	6182174	0	747296	1893695	348318	116224	9688	2141	2	6	117

---

Flowchart

---

grViz("digraph flowchart {
      # node definitions with substituted label text
      node [fontname = Helvetica, shape = rectangle]        
      tab1 [label = '@@1']
      tab2 [label = '@@2']
      tab3 [label = '@@3']
      tab4 [label = '@@4']
      tab5 [label = '@@5']
      tab6 [label = '@@6']

      # edge definitions with the node IDs
      tab1 -> tab2;
      tab2 -> tab3;
      tab3 -> tab4;
      tab4 -> tab5;
      tab5 -> tab6
      }
      
      [1]: paste0('Raw illumina reads (n = ', totals$PreMerge, ')')
      [2]: paste0('Assembled and merged reads (n = ', totals$Merged, ')')
      [3]: paste0('Remove chimeras and low quality reads (n = ', totals$Merged-totals$Filtered-totals$Chimeric, ')')
      [4]: paste0('Cluster reads at 96% sequence identity (n = ', totals$Centroids, ')')
      [5]: paste0('Remove clusters with low support reads  (n = ', totals$Centroidswithsupport, ')')
      [6]: paste0('Remove non-DBLα sequences, final cleaned DBLα sequences  (n = ', totals$Aftercontaminantfiltering, ')')
      ")